Ax Conor Hassan, Nasrulloh Loka, Cen-You Li, Daolang Huang, Paul E. Chang, Yang Yang, Francesco Silvestrin, Samuel Kaski, Luigi Acerbi 4/22/2026

Efficient Autoregressive Inference for Transformer Probabilistic Models

Paper on efficient autoregressive inference for transformer probabilistic models balancing set-conditioning with joint distributions.

Ax Yang Yang, Severi Rissanen, Paul E. Chang, Nasrulloh Loka, Daolang Huang, Arno Solin, Markus Heinonen, Luigi Acerbi 4/22/2026

PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference

Paper on test-time prior adaptation for simulation-based inference using diffusion models for Bayesian inference.

Ax Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fengbin Zhu, Qifan Wang, Fuli Feng 4/22/2026

TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards

TROJail uses trajectory-level optimization with process rewards to learn multi-turn jailbreak strategies against LLMs.

Ax Simon Welker, Bunlong Lay, Maris Hillemann, Tal Peer, Timo Gerkmann 4/22/2026

Real-Time Streamable Generative Speech Restoration with Flow Matching

Stream.FM applies flow matching for real-time streamable speech restoration with 32ms algorithmic latency.

Ax Qiushi Han, David Simchi-Levi, Renfei Tan, Zishuo Zhao 4/22/2026

Multi-agent Adaptive Mechanism Design

DRAM framework combines mechanism design and online learning for sequential multi-agent truthful reporting.

Ax Lars van der Laan, Nathan Kallus 4/22/2026

Fitted Q Evaluation Without Bellman Completeness via Stationary Weighting

Fitted Q-evaluation theory for off-policy reinforcement learning without requiring Bellman completeness using stationary weighting.

Ax Rachmad Vidya Wicaksana Putra, Pasindu Wickramasinghe, Muhammad Shafique 4/22/2026

QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models

QSLM quantization framework with tiered search optimizes spike-driven language models for embedded deployment.

Ax Janvijay Singh, Dilek Hakkani-T\"ur 4/22/2026

Do LLMs Encode Functional Importance of Reasoning Tokens?

Study investigates whether LLMs encode functional importance of individual reasoning tokens for reasoning chain compression.

Ax Zuang Wang, Yongqiang Wang 4/22/2026

Local Updates in Distributed Optimization: Provable Acceleration and Topology Effects

Theoretical analysis of local updates in distributed optimization showing acceleration benefits and topology effects in federated settings.

Ax Basab Jha, Firoj Paudel, Ujjwal Puri, Ethan Henkel, Zhang Yuting, Mateusz Kowalczyk, Mei Huang, Choi Donghyuk, Wang Junhao 4/22/2026

SAGE-32B: Agentic Reasoning via Iterative Distillation

SAGE-32B is a 32B parameter model fine-tuned via iterative distillation for agentic reasoning, task decomposition, and tool usage.

Ax Meiru Zhang, Zaiqiao Meng, Nigel Collier 4/22/2026

Failure Modes in Multi-Hop QA: The Weakest Link Effect and the Recognition Bottleneck

Multi-Focus Attention Instruction probe disentangles recognition vs synthesis failures in multi-hop LLM reasoning.

Ax Hyunjong Ok, Jaeho Lee 4/22/2026

Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models

Study reveals LLMs are highly sensitive to prompt order in multiple-choice QA due to causal attention limitations.

Ax Zhaoyan Gong, Zhiqiang Liu, Songze Li, Xiaoke Guo, Yuanxiang Liu, Xinle Deng, Zhizhen Liu, Lei Liang, Huajun Chen, Wen Zhang 4/22/2026

Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning

Temp-R1 is an autonomous agent for temporal knowledge graph question answering trained via reverse curriculum reinforcement learning.

Ax Jiale Zhao, Ke Fang, Lu Cheng 4/22/2026

When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification

AskBench evaluates and improves LLM ability to request clarification on ambiguous prompts using reinforcement learning with rubric guidance.

Ax Mainak Singha, Sarthak Mehrotra, Paolo Casari, Subhasis Chaudhuri, Elisa Ricci, Biplab Banerjee 4/22/2026

CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation

CLIPoint3D adapts vision-language models like CLIP for 3D point cloud domain adaptation with few-shot unsupervised learning.

Ax Zongyue Qin, Raghavv Goel, Mukul Gagrani, Risheek Garrepalli, Mingu Lee, Yizhou Sun 4/22/2026

ConFu: Contemplate the Future for Better Speculative Sampling

ConFu improves speculative decoding for LLM inference acceleration by enhancing draft model quality to propose better candidate tokens for verification.

Ax Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dohyung Kim, Jiwon Jeon, Dongsheng Li, Yuqing Yang 4/22/2026

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Self-distillation degrades LLM reasoning by suppressing epistemic verbalization of uncertainty; controlled experiments isolate degradation mechanisms.

Ax Caio Vicentino 4/22/2026

PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression

PolarQuant post-training quantization for LLMs uses Hadamard rotation and Gaussian weight distribution for near-lossless compression.

Ax Aastha A K Verma, Anwoy Chatterjee, Mehak Gupta, Tanmoy Chakraborty 4/22/2026

Multilingual Language Models Encode Script Over Linguistic Structure

Analysis reveals multilingual language models organize internal representations by orthographic script rather than linguistic structure across language families.

Ax Tanzim Ahad, Ismail Hossain, Md Jahangir Alam, Sai Puppala, Yoonpyo Lee, Syed Bahauddin Alam, Sajedul Talukder 4/22/2026

Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines

Semantic Intent Fragmentation attack exploits LLM orchestration systems where composed subtasks violate security policy despite individual benignness.

Ax Olga Chetverina 4/22/2026

A Triadic Suffix Tokenization Scheme for Numerical Reasoning

Triadic Suffix Tokenization improves LLM numerical reasoning by partitioning digits into three-digit triads with explicit magnitude markers.

Ax Ryan Faulkner, Anushka Deshpande, David Guzman Piedrahita, Joel Z. Leibo, Zhijing Jin 4/22/2026

Evaluating Cooperation in LLM Social Groups through Elected Leadership

Multi-agent study evaluating whether LLMs can cooperate on resource governance through elected leadership and self-governance mechanisms.

Ax Hongyi Jin, Bohan Hou, Guanjie Wang, Ruihang Lai, Jinqi Chen, Zihao Ye, Yaxing Cai, Yixin Dong, Xinhao Cheng, Zhihao Zhang, Yilong Zhao, Yingyi Huang, Lijie Yang, Jinchen Jiang, Gabriele Oliaro, Jianan Ji, Xupeng Miao, Vinod Grover, Todd C. Mowry, Zhihao Jia, Tianqi Chen 4/22/2026

Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel

Event Tensor abstraction eliminates kernel launch overheads in LLM inference by fusing operators into persistent kernels handling dynamic shapes.

Ax Jon-Paul Cacioli 4/22/2026

The Metacognitive Monitoring Battery: A Cross-Domain Benchmark for LLM Self-Monitoring

Cross-domain metacognitive benchmark for LLMs with 524 items across six cognitive domains using human psychometric methodology.

Ax Baoyou Chen, Hanchen Xia, Peng Tu, Haojun Shi, Shan Mu, Weihao Yuan, Siyu Zhu 4/22/2026

BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation

BARD framework bridges autoregressive and diffusion vision-language models via progressive block merging and stage-wise distillation for efficient inference.

Ax Samrendra Roy, Syed Bahauddin Alam 4/22/2026

Q-SINDy: Quantum-Kernel Sparse Identification of Nonlinear Dynamics with Provable Coefficient Debiasing

Q-SINDy integrates quantum feature maps into sparse identification of nonlinear dynamics, addressing coefficient cannibalization failure mode.

Ax Jiaqi Wang, Haoge Deng, Ting Pan, Yang Liu, Chengyuan Wang, Fan Zhang, Yonggang Qi, Xinlong Wang 4/22/2026

UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models

Novel framework integrating Uniform Discrete Diffusion Models with Group Relative Policy Optimization for stable RL training on discrete generative models.

Ax Terry Leitch 4/22/2026

Benchmarking System Dynamics AI Assistants: Cloud Versus Local LLMs on CLD Extraction and Discussion

Systematic benchmark comparing cloud and open-source LLMs on System Dynamics tasks: causal loop diagram extraction and interactive coaching.

HN tleitch 4/22/2026

Benchmarking Cloud vs. Local LLMs Why back end choice matters more than quant

Incomplete article about arXiv Labs framework; content does not match title about LLM benchmarking.

HN yincrash 4/22/2026

Show HN: Aide – A customizable Android assistant (voice, choose your provider)

Aide: customizable Android voice assistant supporting Claude, OpenAI, or OpenAI-compatible endpoints with on-device encryption.

HN taoh 4/22/2026

Show HN: Open Chronicle – Local Screen Memory for Claude Code and Codex CLI

Open source local screen memory tool for Claude and coding agents; OCR and summarization via local AI; Mac-only Swift app.

HN PrismerAI 4/22/2026

Show HN: Agent harness that turns errors into shared genes

Prismer: infrastructure layer for long-running AI agents with error recovery, persistent memory, and cross-session learning.

HN geoffbp 4/22/2026

The AI engineering stack we built internally – on the platform we ship

Cloudflare's internal AI engineering stack: MCP servers, agent infrastructure, and iMARS tiger team integration for engineering workflow.

HN rmason 4/22/2026

Tests Are Dead, Meticulous Is Here

Marketing copy for Meticulous automated testing tool for AI-generated code; claims to eliminate debugging.

HN MemTensor 4/22/2026

Show HN: MemFactory: Unified Inference and Training Framework for Agent Memory

MemFactory: unified framework for training and inference of memory-augmented LLMs using reinforcement learning for agent memory operations like extraction and retrieval.

HN 101008 4/22/2026

Ask HN: How to get motivation of side projects if you don't need the money?

MemFactory: unified framework for inference and training of memory-augmented LLMs for long-term AI agents using RL optimization.

HN venkatapgummadi 4/22/2026

Ascend – DevSecOps framework with AI-powered merge conflict sync

Technical article on building search engines for AI agents, handling complex query graphs and agent-generated code constraints.

HN devonnull 4/22/2026

Meta to start capturing employee mouse movements, keystrokes for AI training

ASCEND: DevSecOps framework with AI-powered merge conflict resolution integrated into CI/CD pipelines.

HN rjpruitt16 4/22/2026

Layer 8: The coordination protocol AI agents and embedded devices don't have yet

Meta installing tracking software (MCI) on employee computers to capture interactions for AI agent training.

HN inderrr 4/22/2026

Show HN: Govern Anthropic Managed Agents with 3 lines of code

Kuri: Zig-based browser automation tool for AI agents with 464KB binary, 3ms cold start, 16% token efficiency improvement.

HN kitdobyns 4/22/2026

Show HN: Benchmarking how AI models write vulnerable code under pressure

Benchmark study measuring vulnerability patterns in code generated by AI models under time pressure conditions.

HN Anon84 4/22/2026

Google WeatherNext 2 – Our most accurate AI weather forecasting technology

Google WeatherNext 2: state-of-the-art ML models for weather forecasting released to researchers and enterprises.

HN onsari 4/22/2026

Show HN: PayClaw – Give your AI agent a wallet it can spend

PayClaw: tool enabling AI agents to manage wallets and execute financial transactions autonomously.

HN dataviz1000 4/22/2026

Show HN: Group Relative Policy Optimization, visualized step by step

Visualization tool for Group Relative Policy Optimization, an LLM training method.

HN jcviau 4/22/2026

Voxyflow – An AI companion that plans, codes, and ships with you

Voxyflow: personal AI assistant agent that plans, codes, and ships projects. Open source, runs locally. Alpha stage.

HN raunaksingwi 4/22/2026

Ravix – An AI agent that runs on your Claude Code subscription (alpha)

Ravix: autonomous AI agent running on Claude Code subscription, auto-manages email inbox. 60-second setup, no additional costs.

HN compulsivebuild 4/22/2026

Submit your startup profile with Claude or ChatGPT. 60 seconds or less

AI-powered startup profile submission tool using Claude/ChatGPT agents with MCP integration for form filling and validation.

HN annanay 4/22/2026

Show HN: gcx – The Official Grafana Cloud CLI

Grafana Cloud CLI (gcx) enabling AI agents to query production observability without leaving editor.

BL 4/22/2026

Introducing OpenAI Privacy Filter

OpenAI releases open-weight Privacy Filter model for detecting and redacting PII in text. Infrastructure tool for developers building AI applications with privacy protections.

HN stosssik 4/21/2026

How Much Do GPU Clusters Cost?

Analysis of GPU cluster costs for AI/ML companies and spending breakdown for foundation models.